10 papers
ControlRef: Efficient Layout-Guided Multi-Instance Generation via Anchored 4D-RoPE
Yunkai Yang, Yudong Zhang, Xinying Chen +7
Layout-guided multi-instance generation is essential for controllable image synthesis in Multi-Modal Diffusion Transformers (MM-DiTs). However, integrating this capability into uni…
Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs
Wei Ding, Yudong Zhang, Ruobing Xie +3
As foundation models scale toward fusing more heterogeneous visual streams, understanding how diverse encoders interact under joint training becomes a prerequisite for principled d…
MHSA: A Lightweight Framework for Mitigating Hallucinations via Steered Attention in LVLMs
Wei Ding, Yilin Li, Yudong Zhang +4
Large vision-language models (LVLMs) have achieved remarkable performance across diverse multimodal tasks, yet they continue to suffer from hallucinations, generating content that…
Task-Oriented Data Synthesis and Control-Rectify Sampling for Remote Sensing Semantic Segmentation
Yunkai Yang, Yudong Zhang, Kunquan Zhang +4
With the rapid progress of controllable generation, training data synthesis has become a promising way to expand labeled datasets and alleviate manual annotation in remote sensing…
The Security Threat of Compressed Projectors in Large Vision-Language Models
Yudong Zhang, Ruobing Xie, Xingwu Sun +4
The choice of a suitable visual language projector (VLP) is critical to the successful training of large visual language models (LVLMs). Mainstream VLPs can be broadly categorized…
Towards a Comprehensive Scaling Law of Mixture-of-Experts
Guoliang Zhao, Yuhan Fu, Shuaipeng Li +10
Mixture-of-Experts (MoE) models have become the consensus approach for enabling parameter-efficient scaling and cost-effective deployment in large language models. However, existin…